Millisecond X-ray reflectometry and neural network analysis: unveiling fast processes in spin coating

X-ray reflectometry (XRR) is a powerful tool for probing the structural characteristics of nanoscale films and layered structures, which is an important field of nanotechnology and is often used in semiconductor and optics manufacturing. This study introduces a novel approach for conducting quantitative high-resolution millisecond monochromatic XRR measurements. This is an order of magnitude faster than in previously published work. Quick XRR (qXRR) enables real time and in situ monitoring of nanoscale processes such as thin film formation during spin coating. A record qXRR acquisition time of 1.4 ms is demonstrated for a static gold thin film on a silicon sample. As a second example of this novel approach, dynamic in situ measurements are performed during PMMA spin coating onto silicon wafers and fast fitting of XRR curves using machine learning is demonstrated. This investigation primarily focuses on the evolution of film structure and surface morphology, resolving for the first time with qXRR the initial film thinning via mass transport and also shedding light on later thinning via solvent evaporation. This innovative millisecond qXRR technique is of significance for in situ studies of thin film deposition. It addresses the challenge of following intrinsically fast processes, such as thin film growth of high deposition rate or spin coating. Beyond thin film growth processes, millisecond XRR has implications for resolving fast structural changes such as photostriction or diffusion processes.

Interactions Between Offender and Crime Characteristics Leading to a Lethal Outcome in Cases of Sexually-Motivated Abductions

Despite the widespread public concern regarding abduction, research on this type of crime is scarce. This lack of research is even more pronounced when looking at cases that end with the death of the victim. In fact, all of the research looking at lethal outcomes in cases of abductions has focused exclusively on child victims and has failed to consider the interactions at the multivariate level between the factors related to the death of the victim. Therefore, the aim of the study is to identify offender and crime characteristics - as well as their interactions - associated with a lethal outcome in sexually-motivated abductions using a combination of logistic regression and neural network analyses on a sample of 281 cases (81 cases ending with a lethal outcome, random sample of 200 comparison cases). Findings show that sexually-motivated abductions ending with a lethal outcome are more likely to be characterized by an offender who is a loner, forensically aware, and who who uses a weapon and restraints, and who sexually penetrates and beats a known victim. The neural network analysis show that three different pathways lead to a lethal outcome in sexually-motivated abductions. Such findings are important for correctional practices.

Screening and Demulsification Mechanism of Fluorinated Demulsifier Based on Molecular Dynamics Simulation

In order to solve the problem of demulsification difficulties in Liaohe Oilfield, 24 kinds of demulsifiers were screened by using the interface generation energy (IFE) module in the molecular dynamics simulation software Materials Studio to determine the ability of demulsifier molecules to reduce the total energy of the oil–water interface after entering the oil–water interface. Neural network analysis (NNA) and genetic function approximation (GFA) were used as technical means to predict the demulsification effect of the Liaohe crude oil demulsifier. The simulation results show that the SDJ9927 demulsifier with ethylene oxide (EO) and propylene oxide (PO) values of 21 (EO) and 44 (PO) reduced the total energy and interfacial tension of the oil–water interface to the greatest extent, and the interfacial formation energy reached −640.48 Kcal/mol. NNA predicted that the water removal amount of the SDJ9927 demulsifier was 7.21 mL, with an overall error of less than 1.83. GFA predicted that the water removal amount of the SDJ9927 demulsifier was 7.41mL, with an overall error of less than 0.9. The predicted results are consistent with the experimental screening results. SDJ9927 had the highest water removal rate and the best demulsification effect. NNA and GFA had high correlation coefficients, and their R²s were 0.802 and 0.861, respectively. The higher R² was, the more accurate the prediction accuracy was. Finally, the demulsification mechanism of the interfacial film breaking due to the collision of fluorinated polyether demulsifiers was studied. It was found that the carbon–fluorine chain had high surface activity and high stability, which could protect the carbon–carbon bond in the demulsifier molecules to ensure that there was no re-emulsion due to the stirring external force.

Assessment of determinants predicting success on the Saudi Nursing Licensure Examination by employing artificial neural network

BACKGROUND

This study aims to use the artificial neural network as a novel approach to explore factors that determine and predict successful performance of nursing interns in Saudi Arabia on the Saudi Nursing Licensure Examination (SNLE).

MATERIALS AND METHODS

The study employed a cross-sectional, analytic approach. A total of 62 nursing interns were recruited by convenience sampling from the University of Hail to participate. Data collection was conducted from September to December 2019. Descriptive statistics were used to describe the demographic characteristics of the nursing interns and their responses regarding examination determinants. Neural network analysis was used to identify factors that are highly predictive of the success of the nursing interns on the SNLE.

RESULTS

Overall, the nursing interns were undecided (3.94 ± 0.14) about the influential factors determining their success. Their study hours (100%) and grade point average (GPA) (96.9%) were identified as strong determinants reflective of the tenacity and vigor of the nursing interns, based on the predictive power of the model. Meanwhile, age (45.7%), marital status (21.3%), gender (15.2%), and the type of academic program (5.9%) were considered the least important of the sociodemographic variables.

CONCLUSION

Exam preparation activities such as preparation programs, review classes, and exam simulations must be promoted and enhanced to increase the passing tendencies of the nursing interns in the SNLE. The GPA and increased study hours make the most significant contributions to success on the SNLE as compared to other variables such as age, gender, marital status, and the academic program. This study serves as a springboard for nursing educators and administrators in laying tailored strategies to strengthen the nurse interns' GPA and time management.

Applying Machine Learning Approaches to Suicide Prediction Using Healthcare Data: Overview and Future Directions

Objective: Early identification of individuals who are at risk for suicide is crucial in supporting suicide prevention. Machine learning is emerging as a promising approach to support this objective. Machine learning is broadly defined as a set of mathematical models and computational algorithms designed to automatically learn complex patterns between predictors and outcomes from example data, without being explicitly programmed to do so. The model's performance continuously improves over time by learning from newly available data. Method: This concept paper explores how machine learning approaches applied to healthcare data obtained from electronic health records, including billing and claims data, can advance our ability to accurately predict future suicidal behavior. Results: We provide a general overview of machine learning concepts, summarize exemplar studies, describe continued challenges, and propose innovative research directions. Conclusion: Machine learning has potential for improving estimation of suicide risk, yet important challenges and opportunities remain. Further research can focus on incorporating evolving methods for addressing data imbalances, understanding factors that affect generalizability across samples and healthcare systems, expanding the richness of the data, leveraging newer machine learning approaches, and developing automatic learning systems.

Role of Regulatory Non-Coding RNAs in Aggressive Thyroid Cancer: Prospective Applications of Neural Network Analysis

Thyroid cancer (TC) is the most common endocrine malignancy. Most TCs have a favorable prognosis, whereas anaplastic thyroid carcinoma (ATC) is a lethal form of cancer. Different genetic and epigenetic alterations have been identified in aggressive forms of TC such as ATC. Non-coding RNAs (ncRNAs) represent functional regulatory molecules that control chromatin reprogramming, including transcriptional and post-transcriptional mechanisms. Intriguingly, they also play an important role as coordinators of complex gene regulatory networks (GRNs) in cancer. GRN analysis can model molecular regulation in different species. Neural networks are robust computing systems for learning and modeling the dynamics or dependencies between genes, and are used for the reconstruction of large data sets. Canonical network motifs are coordinated by ncRNAs through gene production from each transcript as well as through the generation of a single transcript that gives rise to multiple functional products by post-transcriptional modifications. In non-canonical network motifs, ncRNAs interact through binding to proteins and/or protein complexes and regulate their functions. This article overviews the potential role of ncRNAs GRNs in TC. It also suggests prospective applications of deep neural network analysis to predict ncRNA molecular language for early detection and to determine the prognosis of TC. Validation of these analyses may help in the design of more effective and precise targeted therapies against aggressive TC.

[Assessment of PD-L1 expression using the neural network analysis algorithm in non-small cell lung carcinoma biopsy specimens]

Neural network analysis of digital copies of histological micropreparations is one of the methods used to standardize quantitative continuous data. PD-L1 (22C3) biomarker expression in metastatic non-small cell lung carcinomas without mutations in the EGFR, ALK, and ROS1 genes serves as an indication for the use of pembrolizumab for the first-line therapy.

OBJECTIVE

To quantify PD-L1 biomarker expression in non-small cell lung carcinomas using the neural network analysis of digital copies of histological micropreparations.

MATERIAL AND METHODS

Immunohistochemical study of PD-L1 (22C3) expression was performed on 96 non-small cell lung carcinoma biopsy specimens. The digital copies of histological micropreparations were processed by the QuPath software neural network analysis module.

RESULTS

The neural network analysis module segmented tumor, stroma, and artifacts in the micropreparations, showing a sufficient level of agreement with a visual assessment. Digital image analysis quantified stained tumor cells in the high PD-L1 expression group and showed 96% agreement rate versus visual assessment. However, the group of tumors without PD-L1 expression versus visual assessment showed a low (58%) agreement rate.

CONCLUSION

The neural network analysis algorithm is applicable to the study of digital copies of histological micropreparations containing tumor, stroma, and artifacts. The algorithm allows for quantitative immunohistochemical assessment of PD-L1 expression in tumor cells. The algorithm can quantify the immunohistochemically detected expression of PD-L1 in tumor cells.

Application of Neural Network and Cluster Analyses to Differentiate TCM Patterns in Patients With Breast Cancer

Background and Purpose

Pattern differentiation is a critical element of the prescription process for Traditional Chinese Medicine (TCM) practitioners. Application of advanced machine learning techniques will enhance the effectiveness of TCM in clinical practice. The aim of this study is to explore the relationships between clinical features and TCM patterns in breast cancer patients.

Methods

The dataset of breast cancer patients receiving TCM treatment was recruited from a single medical center. We utilized a neural network model to standardize terminologies and address TCM pattern differentiation in breast cancer cases. Cluster analysis was applied to classify the clinical features in the breast cancer patient dataset. To evaluate the performance of the proposed method, we further compared the TCM patterns to therapeutic principles of Chinese herbal medication in Taiwan.

Results

A total of 2,738 breast cancer cases were recruited and standardized. They were divided into 5 groups according to clinical features via cluster analysis. The pattern differentiation model revealed that liver-gallbladder dampness-heat was the primary TCM pattern identified in patients. The main therapeutic goals of the top 10 Chinese herbal medicines prescribed for breast cancer patients were to clear heat, drain dampness, and detoxify. These results demonstrated that the neural network successfully identified patterns from a dataset similar to the prescriptions of TCM clinical practitioners.

Conclusion

This is the first study using machine-learning methodology to standardize and analyze TCM electronic medical records. The patterns revealed by the analyses were highly correlated with the therapeutic principles of TCM practitioners. Machine learning technology could assist TCM practitioners to comprehensively differentiate patterns and identify effective Chinese herbal medicine treatments in clinical practice.

Systematic Review and Neural Network Analysis to Define Predictive Variables in Implantable Motor Cortex Stimulation to Treat Chronic Intractable Pain

Implantable motor cortex stimulation (iMCS) has been performed for >25 years to treat various intractable pain syndromes. Its effectiveness is highly variable and, although various studies revealed predictive variables, none of these were found repeatedly. This study uses neural network analysis (NNA) to identify predictive factors of iMCS treatment for intractable pain. A systematic review provided a database of patient data on an individual level of patients who underwent iMCS to treat refractory pain between 1991 and 2017. Responders were defined as patients with a pain relief of >40% as measured by a numerical rating scale (NRS) score. NNA was carried out to predict the outcome of iMCS and to identify predictive factors that impacted the outcome of iMCS. The outcome prediction value of the NNA was expressed as the mean accuracy, sensitivity, and specificity. The NNA furthermore provided the mean weight of predictive variables, which shows the impact of the predictive variable on the prediction. The mean weight was converted into the mean relative influence (M), a value that varies between 0 and 100%. A total of 358 patients were included (202 males [56.4%]; mean age, 54.2 ±13.3 years), 201 of whom were responders to iMCS. NNA had a mean accuracy of 66.3% and a sensitivity and specificity of 69.8% and 69.4%, respectively. NNA further identified 6 predictive variables that had a relatively high M: 1) the sex of the patient (M = 19.7%); 2) the origin of the lesion (M = 15.1%); 3) the preoperative numerical rating scale score (M = 9.2%); 4) preoperative use of repetitive transcranial magnetic stimulation (M = 7.3%); 5) preoperative intake of opioids (M = 7.1%); and 6) the follow-up period (M = 13.1%). The results from the present study show that these 6 predictive variables influence the outcome of iMCS and that, based on these variables, a fair prediction model can be built to predict outcome after iMCS surgery. PERSPECTIVE: The presented NNA analyzed the functioning of computational models and modeled nonlinear statistical data. Based on this NNA, 6 predictive variables were identified that are suggested to be of importance in the improvement of future iMCS to treat chronic pain.

Computer-assisted cytologic diagnosis in pancreatic FNA: An application of neural networks to image analysis

BACKGROUND

Fine-needle aspiration (FNA) biopsy is an accurate method for the diagnosis of solid pancreatic masses. However, a significant number of cases still pose a diagnostic challenge. The authors have attempted to design a computer model to aid in the diagnosis of these biopsies.

METHODS

Images were captured of cell clusters on ThinPrep slides from 75 pancreatic FNA cases (20 malignant, 24 benign, and 31 atypical). A K-means clustering algorithm was used to segment the cell clusters into separable regions of interest before extracting features similar to those used for cytomorphologic assessment. A multilayer perceptron neural network (MNN) was trained and then tested for its ability to distinguish benign from malignant cases.

RESULTS

A total of 277 images of cell clusters were obtained. K-means clustering identified 68,301 possible regions of interest overall. Features such as contour, perimeter, and area were found to be significantly different between malignant and benign images (P <.05). The MNN was 100% accurate for benign and malignant categories. The model's predictions from the atypical data set were 77% accurate.

CONCLUSIONS

The results of the current study demonstrate that computer models can be used successfully to distinguish benign from malignant pancreatic cytology. The fact that the model can categorize atypical cases into benign or malignant with 77% accuracy highlights the great potential of this technology. Although further study is warranted to validate its clinical applications in pancreatic and perhaps other areas of cytology as well, the potential for improved patient outcomes using MNN for image analysis in pathology is significant. Cancer Cytopathol 2017;125:926-33. © 2017 American Cancer Society.